Oktoaria, Kevin (2023) Sistem Pemantauan Cuaca dan Peringatan Kecepatan Angin Berbasis IoT dan Machine Learning Sebagai Mitigasi Risiko Kecelakaan Kerja Pada Kegiatan Bongkar Muat Petikemas di Terminal Petikemas Nilam. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5027201046-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5027201046-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (3MB) | Request a copy |
Abstract
Kegiatan bongkar muat petikemas di pelabuhan sangat dekat dengan risiko kecelakaan kerja dimana salah satu faktor penyebab terjadinya kecelakaan kerja adalah faktor cuaca. Jumlah kejadian kecelakaan kerja di Terminal Petikemas Nilam selama Tahun 2023 adalah sebanyak 17 kasus. Penelitian ini bertujuan untuk membangun sebuah sistem pemantauan cuaca dan peringatan kecepatan angin berbasis Internet of Things (IoT) dan machine learning sebagai mitigasi risiko kecelakaan kerja pada kegiatan bongkar muat petikemas di TPK Nilam. Dengan menggunakan sensor cuaca IoT, sistem ini dibangun untuk mengukur parameter cuaca, sehingga memungkinkan sistem prediksi kecepatan angin, arah angin, temperatur, dan intensitas hujan berbasis machine learning dapat bekerja pada data tersebut. Metode machine learning random forest yang digunakan, mampu mengumpulkan dan mengirimkan data secara real-time ke sistem pemantauan untuk mengidentifikasi potensi bahaya cuaca dan mengeluarkan peringatan dini kepada petugas bongkar muat. Kinerja model menunjukkan performa lebih baik, dengan nilai untuk kecepatan angin mean absolute error (MAE) mencapai 0,15, mean squared error (MSE) sebesar 0,04, dan root mean squared error (RMSE) mencapai 0,20. Selanjutnya terdapat arah angin dengan mean absolute error (MAE) sebesar 11,1, mean squared error (MSE) sebesar 16,9, dan root mean squared error (RMSE) sebesar 13. Lalu untuk temperatur terdapat mean absolute error (MAE) sebesar 0,2, mean squared error (MSE) sebesar 0,05, dan root mean squared error (RMSE) sebesar 0,24. Terakhir, terdapat intensitas hujan dengan mean absolute error (MAE) sebesar 8,8, mean squared error (MSE) sebesar 10,16, dan root mean squared error (RMSE) sebesar 10,08. Website yang mudah diakses dapat menampilkan alert system bila kecepatan angin mencapai 17 m/s pertanda angin kencang sesuai Skala Beaufort. Output yang dihasilkan adalah prediksi cuaca untuk satu jam kedepan sehingga dapat meningkatkan kewaspadaan para pekerja dan petugas bongkar muat petikemas sebagai mitigasi risiko kecelakaan kerja. Implementasi sistem ini di Terminal Petikemas Nilam diharapkan dapat menjadi langkah mitigasi yang efektif terhadap risiko kecelakaan kerja pada kegiatan bongkar muat petikemas.
=============================================================================================================================
Container loading and unloading activities at the port are very close to the risk of work accidents where one of the factors causing work accidents is weather. The number of work accidents at the Nilam Container Terminal during 2023 was 17 cases. This research aims to build a weather monitoring and wind speed warning system based on the Internet of Things (IoT) and machine learning as a mitigation of work accident risks in container loading and unloading activities at TPK Nilam. Using IoT weather sensors, the system is built to measure weather parameters, allowing the machine learning-based wind speed, wind direction, temperature, and raindrop intensity prediction system to work on the data. The Machine Learning Random Forest method used, is able to collect and send real-time data to the monitoring system to identify potential weather hazards and issue early warnings to stevedores. Model performance shows better performance, with values for wind speed mean absolute error (MAE) reaching 0,15, mean squared error (MSE) of 0,04, and root mean squared error (RMSE) reaching 0,20. Furthermore, there is wind direction with a mean absolute error (MAE) of 11,1, mean squared error (MSE) of 16,9, and root mean squared error (RMSE) of 13. Then for temperature there is a mean absolute error (MAE) of 0,2, mean squared error (MSE) of 0,05, and root mean squared error (RMSE) of 0,24. Finally, there is rain intensity with a mean absolute error (MAE) of 8,8, mean squared error (MSE) of 10,16, and root mean squared error (RMSE) of 10,08. The easily accessible website can display an alert system when the wind speed reaches 17 m/s, a sign of strong winds according to the Beaufort Scale. The resulting output is a prediction of weather for the next hour so that it can increase the vigilance of workers and container loading and unloading officers as a mitigation of the risk of work accidents. The implementation of this system at the Nilam Container Terminal is expected to be an effective mitigation measure against the risk of work accidents in container loading and unloading activities.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Weather, IoT, Machine Learning, Cuaca |
| Subjects: | T Technology > T Technology (General) > T174 Technological forecasting T Technology > TD Environmental technology. Sanitary engineering > TD171.75 Climate change mitigation T Technology > TD Environmental technology. Sanitary engineering > TD890 Global Environmental Monitoring System |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis |
| Depositing User: | Kevin Oktoaria |
| Date Deposited: | 19 Feb 2024 02:24 |
| Last Modified: | 19 Feb 2024 02:24 |
| URI: | http://repository.its.ac.id/id/eprint/107422 |
Actions (login required)
 |
View Item |